Towards the Training of Deeper Predictive Coding Neural Networks

Abstract: Predictive coding networks trained with equilibrium propagation are neural models that perform inference through an iterative energy minimization process. Previous studies have demonstrated their effectiveness in shallow architectures, but show significant performance degradation when depth exceeds five to seven layers. In this work, we show that the reason behind this degradation is due to exponentially imbalanced errors between layers during weight updates, and predictions from the previous layer not being effective in guiding updates in deeper layers. We address the first issue by introducing two novel methods to optimize the latent variables that use precision-weighting to re-balance the distribution of energy among layers during the `relaxation phase', and the second issue by proposing a novel weight update mechanism that reduces error accumulation in deeper layers. Empirically, we test our methods on a large number of image classification tasks, resulting in large improvements in test accuracy across networks with more than seven layers, with performances comparable to those of backprop on similar models. These findings suggest that a better understanding of the relaxation phase is important to train models using equilibrium propagation at scale, and open new possibilities for their application in complex tasks.